Stacked What-Where Auto-encoders

We present a novel architecture, the "stacked what-where auto-encoders" (SWWAE), which integrates discriminative and generative pathways and provides a unified approach to supervised, semi-supervised and unsupervised learning without relying on sampling during training. An instantiation of SWWAE uses a convolutional net (Convnet) (LeCun et al. (1998)) to encode the input, and employs a deconvolutional net (Deconvnet) (Zeiler et al. (2010)) to produce the reconstruction. The objective function includes reconstruction terms that induce the hidden states in the Deconvnet to be similar to those of the Convnet. Each pooling layer produces two sets of variables: the "what" which are fed to the next layer, and its complementary variable "where" that are fed to the corresponding layer in the generative decoder.

• Publication year

  2015

• Venue

  arXiv.org

• Publication date

  2015-06-08

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1506.02351
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Statistical Learning Theory

  2021cited by this paper
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Training Very Deep Networks

  2015cited by this paper
• Under Review as a Conference Paper at Iclr 2016 Predicting Distributions with Linearizing Belief Networks

  2015cited by this paper
• Learning to Linearize Under Uncertainty

  2015cited by this paper
• Semi-supervised Learning with Ladder Networks

  2015cited by this paper
• Lateral Connections in Denoising Autoencoders Support Supervised Learning

  2015cited by this paper
• Striving for Simplicity: The All Convolutional Net

  2014cited by this paper
• A Winner-Take-All Method for Training Sparse Convolutional Autoencoders

  2014cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Stable and Efficient Representation Learning with Nonnegativity Constraints

  2014cited by this paper
• Discriminative Unsupervised Feature Learning with Convolutional Neural Networks

  2014cited by this paper
• Deeply-Supervised Nets

  2014cited by this paper
• Semi-supervised Learning with Deep Generative Models

  2014cited by this paper
• Convolutional Kernel Networks

  2014cited by this paper
• Fractional Max-Pooling

  2014cited by this paper
• An Analysis of Unsupervised Pre-training in Light of Recent Advances

  2014cited by this paper
• Winner-Take-All Autoencoders

  2014cited by this paper
• k-Sparse Autoencoders

  2013cited by this paper
• Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks

  2013cited by this paper
• Multi-Task Bayesian Optimization

  2013cited by this paper
• Improving neural networks by preventing co-adaptation of feature detectors

  2012cited by this paper
• Unsupervised Feature Learning for RGB-D Based Object Recognition

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Contractive Auto-Encoders: Explicit Invariance During Feature Extraction

  2011influential reference
• The Manifold Tangent Classifier

  2011cited by this paper
• Transforming Auto-Encoders

  2011cited by this paper
• Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction

  2011cited by this paper
• Unsupervised Learning of Sparse Features for Scalable Audio Classification

  2011cited by this paper
• Why Does Unsupervised Pre-training Help Deep Learning?

  2010cited by this paper
• Learning Convolutional Feature Hierarchies for Visual Recognition

  2010cited by this paper
• Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition

  2010cited by this paper
• Deconvolutional networks

  2010cited by this paper
• Learning Fast Approximations of Sparse Coding

  2010cited by this paper
• Learning invariant features through topographic filter maps

  2009cited by this paper
• Classification using discriminative restricted Boltzmann machines

  2008cited by this paper
• Deep learning via semi-supervised embedding

  2008cited by this paper
• Semi-supervised learning of compact document representations with deep networks

  2008cited by this paper
• Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition

  2007cited by this paper
• A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images

  2007cited by this paper
• A Fast Learning Algorithm for Deep Belief Nets

  2006cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper
• Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition

  year unknowncited by this paper

• Navigating beyond backpropagation: on alternative training methods for deep neural networks

  2025cites this paper
• ACACM: Autoencoder and Confidence-Assisted Classification Model for Network Anomaly Detection

  2025cites this paper
• An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering

  2025cites this paper
• ELSA: Expanded Latent Space Autoencoder for Image Feature Extraction and Classification

  2024cites this paper
• Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence

  2024cites this paper
• Image Based Spacecraft Health Evaluation by AIML Based Expert System

  2024cites this paper
• Automatic Face Image Restoration Based on an Improved Generative Adversarial Network

  2024cites this paper
• A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications

  2024cites this paper
• ST-LP: self-training and label propagation for semi-supervised classification

  2024influential citation
• Self-training and Label Propagation for Semi-supervised Classification

  2023cites this paper
• Contrastive Representation Disentanglement for Clustering

  2023cites this paper
• Electroencephalography artifact removal based on an autoencoder deep network

  2023cites this paper
• Mine local homogeneous representation by interaction information clustering with unsupervised learning in histopathology images

  2023cites this paper
• Linking Team-level and Organization-level Governance in Machine Learning Operations through Explainable AI and Responsible AI Connector

  2023cites this paper
• Deep Learning based Driving Posture Stability Analysis for People with Mobility Challenges

  2023cites this paper
• WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification

  2023cites this paper
• Channel Configuration for Neural Architecture: Insights from the Search Space

  2023cites this paper
• CLC: Cluster Assignment via Contrastive Representation Learning

  2023cites this paper
• ExpertNet: A Symbiosis of Classification and Clustering

  2022cites this paper
• Improving automated visual fault inspection for semiconductor manufacturing using a hybrid multistage system of deep neural networks

  2022cites this paper
• Semi-Supervised Super-Resolution

  2022cites this paper
• An effective automatic segmentation of abdominal adipose tissue using a convolution neural network.

  2022cites this paper
• DECK: Model Hardening for Defending Pervasive Backdoors

  2022influential citation
• Re-thinking model robustness from stability: a new insight to defend adversarial examples

  2022cites this paper
• Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection

  2022cites this paper
• Maritime Radar Target Detection Using Convolutional Neural Networks

  2022cites this paper
• ProFeat: Unsupervised image clustering via progressive feature refinement

  2022cites this paper
• 'Labelling the Gaps': A Weakly Supervised Automatic Eye Gaze Estimation

  2022cites this paper
• Convolutional dynamic auto-encoder: a clustering method for semantic images

  2022cites this paper
• Self-Supervised Self-Organizing Clustering Network: A Novel Unsupervised Representation Learning Method

  2022cites this paper
• Robust color image hashing using convolutional stacked denoising auto-encoders for image authentication

  2021cites this paper
• Learning the Precise Feature for Cluster Assignment

  2021influential citation
• Deep learning for abdominal adipose tissue segmentation with few labelled samples

  2021cites this paper
• Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering

  2021cites this paper
• Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decomposition

  2021cites this paper
• A Comparative Review of Recent Few-Shot Object Detection Algorithms

  2021cites this paper
• Learning Deep Representation of The Emotion Speech Signal

  2021cites this paper
• Deep Learning for Reconstructing Low-Quality FTIR and Raman Spectra—A Case Study in Microplastic Analyses

  2021cites this paper
• Unsupervised deep clustering via contractive feature representation and focal loss

  2021cites this paper
• RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss

  2021cites this paper
• A Latent Variable Augmentation Method for Image Categorization with Insufficient Training Samples

  2021cites this paper
• MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering

  2021cites this paper
• Adversarial Network for Photographic Image Synthesis from Fine-grained Captions

  2021cites this paper
• Improving Memory Banks for Unsupervised Learning with Large Mini-Batch, Consistency and Hard Negative Mining

  2021cites this paper
• Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders

  2021cites this paper
• The Single-Noun Prior for Image Clustering

  2021cites this paper
• Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations

  2021cites this paper
• ReRankMatch: Semi-Supervised Learning with Semantics-Oriented Similarity Representation

  2021cites this paper
• Supplementary material for “Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders”

  2021cites this paper
• Concurrent Discrimination and Alignment for Self-Supervised Feature Learning

  2021cites this paper
• Meta-Semi: A Meta-learning Approach for Semi-supervised Learning

  2020influential citation
• Whitening for Self-Supervised Representation Learning

  2020influential citation
• Probabilistic Structural Latent Representation for Unsupervised Embedding

  2020cites this paper
• Learning To Classify Images Without Labels

  2020cites this paper
• Generative Feedback Explains Distinct Brain Activity Codes for Seen and Mental Images.

  2020cites this paper
• Image Embedded Segmentation: Uniting Supervised and Unsupervised Objectives for Segmenting Histopathological Images

  2020cites this paper
• Anisotropic Convolution for Image Classification

  2020cites this paper
• Periodic Astrometric Signal Recovery Through Convolutional Autoencoders

  2020cites this paper
• Face Restoration Based on GANs and NST

  2020cites this paper
• Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics

  2020cites this paper
• CompressNet: Generative Compression at Extremely Low Bitrates

  2020cites this paper
• Towards Robust Pattern Recognition: A Review

  2020cites this paper
• Soft Autoencoder and Its Wavelet Adaptation Interpretation

  2020cites this paper
• On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks

  2020cites this paper
• Unsupervised Deep Learning via Affinity Diffusion

  2020cites this paper
• GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering

  2020cites this paper
• Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images

  2020cites this paper
• Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition

  2020cites this paper
• Robust Facial Landmark Detection via Aggregation on Geometrically Manipulated Faces

  2020cites this paper
• CSAERNet: An Efficient Deep Learning Architecture for Image Classification

  2020cites this paper
• Robust Cumulative Crowdsourcing Framework Using New Incentive Payment Function and Joint Aggregation Model

  2020cites this paper
• ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring

  2020cites this paper
• EnAET: A Self-Trained Framework for Semi-Supervised and Supervised Learning With Ensemble Transformations

  2020cites this paper
• Image Embedded Segmentation: Combining Supervised and Unsupervised Objectives through Generative Adversarial Networks

  2020influential citation
• Biologically Inspired Hexagonal Deep Learning For Hexagonal Image Generation

  2020cites this paper
• Unsupervised Foveal Vision Neural Networks with Top-Down Attention

  2020cites this paper
• Structural Prior Driven Regularized Deep Learning for Sonar Image Classification

  2020cites this paper
• Self-supervised representation learning by predicting visual permutations

  2020cites this paper
• Deep Learning Models Based on Image Classification: A Review

  2020cites this paper
• Deinterleaving of Pulse Streams With Denoising Autoencoders

  2020cites this paper
• On the Road With 16 Neurons: Towards Interpretable and Manipulable Latent Representations for Visual Predictions in Driving Scenarios

  2020cites this paper
• Supervised Deep Sparse Coding Networks for Image Classification

  2020cites this paper
• Convolutional Neural Network with Spatial-Variant Convolution Kernel

  2020cites this paper
• A method of face repair based on encoder-decoder and dual discrimination network

  2020cites this paper
• Regression Based Clustering by Deep Adversarial Learning

  2020cites this paper
• Stochastic Loss Function

  2020cites this paper
• Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image Classification

  2020cites this paper
• Multi-level Feature Learning on Embedding Layer of Convolutional Autoencoders and Deep Inverse Feature Learning for Image Clustering

  2020cites this paper
• Improving Self-Organizing Maps with Unsupervised Feature Extraction

  2020cites this paper
• Graph Regularized Variational Ladder Networks for Semi-Supervised Learning

  2020cites this paper
• Using convolutional neural network autoencoders to understand unlabeled data

  2019cites this paper
• Conditional Neural Style Transfer with Peer-Regularized Feature Transform

  2019cites this paper
• FMnet: Iris Segmentation and Recognition by Using Fully and Multi-Scale CNN for Biometric Security

  2019cites this paper
• Mining the displacement of max-pooling for text recognition

  2019cites this paper
• Label Prediction Framework For Semi-Supervised Cross-Modal Retrieval

  2019cites this paper
• MixMatch: A Holistic Approach to Semi-Supervised Learning

  2019cites this paper
• Graph U-Nets

  2019cites this paper
• Réseaux de neurones semi-supervisés pour la segmentation sémantique en télédétection

  2019cites this paper
• Using Convolutional Neural Networks to Extract Shift-Invariant Features from Unlabeled Data

  2019cites this paper
• CAEN: A Deep Learning Approach to Mobile App Traffic Identification

  2019cites this paper